Unbiased Mean Teacher for Cross-domain Object Detection

Abstract

Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maximally exploit the expertise of the teacher model. Moreover, for the student model, we alleviate its bias by augmenting training samples with pixel-level adaptation. Finally, for the teaching process, we employ an out-of-distribution estimation strategy to select samples that most fit the current model to further enhance the cross-domain distillation process. By tackling the model bias issue with these strategies, our UMT model achieves mAPs of 44.1%, 58.1%, 41.7%, and 43.1% on benchmark datasets Clipart1k, Watercolor2k, Foggy Cityscapes, and Cityscapes, respectively, which outperforms the existing state-of-the-art results in notable margins. Our implementation is available at https://github.com/kinredon/umt.

arXiv commentAccepted by CVPR2021

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Semantic Foggy Scene Understanding with Synthetic Data
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
• Self-ensembling for visual domain adaptation
• Wasserstein Distance Based Domain Adaptation for Object Detection
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection